diff options
author | David Brownell <david-b@pacbell.net> | 2007-05-25 18:47:47 -0700 |
---|---|---|
committer | Haavard Skinnemoen <hskinnemoen@atmel.com> | 2007-07-18 20:45:50 +0200 |
commit | c6083cd61b5a64a1c73d1634744382f54cb99595 (patch) | |
tree | 4ad4409a074a9de87a03bc2162d27e326f2c0498 /arch | |
parent | 8b4a40809e5330c9da5d20107d693d92d73b31dc (diff) | |
download | linux-c6083cd61b5a64a1c73d1634744382f54cb99595.tar.bz2 |
[AVR32] faster avr32 unaligned access
Use a more conventional implementation for unaligned access, and include
an AT32AP-specific optimization: the CPU will handle unaligned words.
The result is always faster and smaller for 8, 16, and 32 bit values.
For 64 bit quantities, it's presumably larger.
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Haavard Skinnemoen <hskinnemoen@atmel.com>
Diffstat (limited to 'arch')
0 files changed, 0 insertions, 0 deletions